Adversarial Parametric Pose Prior

12/08/2021
by   Andrey Davydov, et al.
0

The Skinned Multi-Person Linear (SMPL) model can represent a human body by mapping pose and shape parameters to body meshes. This has been shown to facilitate inferring 3D human pose and shape from images via different learning models. However, not all pose and shape parameter values yield physically-plausible or even realistic body meshes. In other words, SMPL is under-constrained and may thus lead to invalid results when used to reconstruct humans from images, either by directly optimizing its parameters, or by learning a mapping from the image to these parameters. In this paper, we therefore learn a prior that restricts the SMPL parameters to values that produce realistic poses via adversarial training. We show that our learned prior covers the diversity of the real-data distribution, facilitates optimization for 3D reconstruction from 2D keypoints, and yields better pose estimates when used for regression from images. We found that the prior based on spherical distribution gets the best results. Furthermore, in all these tasks, it outperforms the state-of-the-art VAE-based approach to constraining the SMPL parameters.

READ FULL TEXT

page 3

page 8

page 12

page 14

research
07/31/2019

Learning to Dress 3D People in Generative Clothing

Three-dimensional human body models are widely used in the analysis of h...
research
06/22/2021

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

In this paper, we aim to create generalizable and controllable neural si...
research
04/05/2021

3D Human Body Reshaping with Anthropometric Modeling

Reshaping accurate and realistic 3D human bodies from anthropometric par...
research
03/11/2022

FLAG: Flow-based 3D Avatar Generation from Sparse Observations

To represent people in mixed reality applications for collaboration and ...
research
03/13/2023

PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation

Human pose and shape (HPS) estimation methods achieve remarkable results...
research
01/17/2021

S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling

Constructing and animating humans is an important component for building...
research
03/16/2023

Diffusion-HPC: Generating Synthetic Images with Realistic Humans

Recent text-to-image generative models have exhibited remarkable abiliti...

Please sign up or login with your details

Forgot password? Click here to reset